Sedan den globala finanskrisen 2008 har flera stora regelverk införts för att säkerställa att banker hanterar risker på sunt sätt. Bland dessa regelverk är Basel II som infört kapitalkrav för kreditrisk som baseras på Sannolikhet för Fallissemang och Förlust Givet Fallissemang. Basel II Advanced Internal-Based Approach ger banker möjligheten att skatta dessa riskmått för enskilda portföljer och göra interna kreditriskvärderingar. I överensstämmelse med Advanced Internal-Based-rating undersöker denna uppsats användningen av en Error Correction Model för modellering av Sannolikhet för Fallissemang. En modell som visat sin styrka inom stresstestning. Vidare implementeras en funktion för Förlust Givet Fallissemang som binder samman Sannolikhet för Fallissemang och Förlust Givet Fallissemang med systematisk risk. Error Correction Modellen modellerar Sannolikhet för Fallissemang av en SME-portfölj från en av de "fyra stora" bankerna i Sverige. Modellen utvärderas och stresstestas med Europeiska Bankmyndighetens  stresstestscenario 2016  och analyseras, med lovande resultat. / Since the global financial crisis of 2008, several big regulations have been implemented to assure that banks follow sound risk management. Among these are the Basel II Accords that implement capital requirements for credit risk. The core measures of credit risk evaluation are the Probability of Default and Loss Given Default. The Basel II Advanced Internal-Based-Rating Approach allows banks to model these measures for individual portfolios and make their own evaluations. This thesis, in compliance with the Advanced Internal-Based-rating approach, evaluates the use of an Error Correction Model when modeling the Probability of Default. A model proven to be strong in stress testing. Furthermore, a Loss Given Default function is implemented that ties Probability of Default and Loss Given Default to systematic risk. The Error Correction Model is implemented on an SME portfolio from one of the "big four" banks in Sweden. The model is evaluated and stress tested with the European Banking Authority's 2016 stress test scenario and analyzed, with promising results.

Cette thèse de doctorat composée de trois chapitres contribue au développement de la problématique sur la sélection de modèle de volatilité de type GARCH. Le premier chapitre propose une étude de simulation sur la sélection de modèles dans le cadre spécifique des modèles à changement de régimes. On propose des expériences de simulation permettant de mettre en évidence l'inefficacité des critères de sélection usuels dans des cas particuliers, ce qui peut conduire à des erreurs de spécification lors du choix de modèle. Le deuxième chapitre propose un test du multiplicateur de Lagrange de mauvaise spécification dans les modèles GARCH univariés. L'hypothèse nulle admet que le processus générateur des données est un modèle GARCH linéaire tandis que sous l'hypothèse alternative il correspond à une forme fonctionnelle inconnue qui est linéarisée à l’aide d’un développement de Taylor. On illustre le test dans une application empirique sur les taux de change. Le dernier chapitre étudie l'impact du prix du pétrole sur les spreads de Credit Default Swaps souverains de deux pays exportateurs de pétrole: le Vénézuela et la Russie. Utilisant des données récentes, nous trouvons que les rendements du prix du pétrole impactent les spread de CDS souverains du Vénézuela directement alors que cela passe par le canal du taux de change pour la Russie. Ce chapitre emploie des méthodes statistiques avancées, notamment l'utilisation de modèles à changement de régimes Markoviens. Finalement, l'appendice propose le manuel de la toolbox MSGtool (Matlab) qui propose une collection de fonctions pour l'étude des modèles à changement de régimes Markoviens. La toolbox est très user-friendly. / This Ph.D. thesis composed by three chapters contributes to the development of model selection in GARCH-type models.The first chapter investigates whether the most common selection criteria lead to choose the right specification in a regime switching framework. We propose simulation experiments which reveal the inefficiency of some selection criteria in particular cases which lead to misspecification. Depending on the Data Generating Process used in the experiments, great care is needed when choosing a criterion.In the second chapter, a misspecication test for GARCH-type models is presented. We propose a Lagrange Multiplier type test based on a Taylor expansion to distinguish between (G)ARCH models and unknown nonlinear GARCH-type models. This test can be seen as a general misspecication test. We investigate the size and the power of this test through Monte Carlo experiments. We show the usefulness of our test with an illustrative empirical example based on daily exchange rate returns.In the third chapter, we study the impact of oil price returns on sovereign Credit Default Swaps (CDS) spreads for two major oil producers, Russia and Venezuela. Using daily spreads from 2008 to 2015, we find that crude oil price returns are a critical determinant of Venezuela CDS spreads changes, but does not explain significantly Russian CDS spreads. Indeed, oil prices seem to impact Russian CDS spreads through the exchange rates canal. Finally, we propose as an appendix the manual of the MSGtool, a MATLAB toolbox, which provides a collection of functions for the simulation and estimation of a large variety of Markov Switching GARCH (MSG) models.

People are not always rational, rely on heuristics and are influenced by situational factors being conducive to biased decisions. Hence, the decision outcome cannot be explained by consumers’ preferences exclusively. This offers opportunities to service managers to steer the decision outcome into a desirable direction by a beneficial design of situational factors. In contrast to the discussed opportunities, situational factors can also become a pitfall for researchers and managers. I show that situational factors may compromise the validity of research results based on self reports in a service context, because the reported scores of research participants may be biased. Three perspectives related to service management are distinguished in this thesis: First, the customer independently of the service provider; second, the interaction of customer and service provider; third, the service provider independently of the customer. From the perspective of the customer, I investigate the impact of different defaults in a customization process on the decision outcome of different types of customers. From the perspective of the customer and service provider interaction, I point out a new solution to overcome a dilemma related to service productivity. Finally, from the perspective of the service provider, the possible contamination of service related constructs by socially desirable responding is examined.

We examine the impact of Mergers & Acquisitions on credit- and investment risk using a sample of 402 acquisitions by 215 Swedish firms from 2000 to 2020. We find significant evidence that, on average, M&A increases the credit risk and inversely decreases the investment risk of the acquiring firm. Our results indicate that firm credit risk however is positively correlated with investment risk. After controlling for specific deal- and firm characteristics, our findings suggest that managerial hubris decreases the level of credit risk and increases the level of investment risk in acquiring firms. Our results are consistent with the asymmetric information hypothesis that managers may exploit the volatility of their stock price to hide risk-increasing activities. We also observe that acquirers with high pre-deal credit risk undertake acquisitions that decrease credit risk and increase investment risk. We find no significant impact from neither method of payment nor valuation errors.

Le phénomène de contagion, les hypothèses d'efficience et les transferts de volatilité sont parmi les théories économiques les plus importantes, car elles fournissent une vision globale sur la stabilité financière. Or, elles restent les moins comprises depuis les récentes crises récentes. Ainsi, cette thèse propose de fournir aux régulateurs économiques, aux investisseurs et aux acteurs du marché financier une vision actualisée du comportement dynamique des marchés mondiaux des Credit Default Swaps (CDS): efficacité informationnelle, interaction avec d'autres marchés financiers internationaux et exposition au risque systémique. La dynamique en constante mutation de ces marchés associée à l'évolution constante des politiques de réglementation a suscité un enthousiasme mondial pour l'étude comportementale des marchés des CDS, auquel nous contribuons à travers cinq essais interconnectés. Nous discutons, dans le premier essai, les faits stylisés des données des CDS souverains à travers l'estimation de 9 modèles de type GARCH. Ce chapitre compare les performances de plusieurs modèles prédictifs de volatilité linéaire et non linéaire et prenant en compte différentes caractéristiques financières des séries statistiques. L'application de ces modèles aux spreads de CDS de 38 pays révèle que le pouvoir prédictif de ces modèles dépend de leur capacité à capturer les faits stylisés des CDS souverains pendant l'estimation du processus de la variance. En effet, les modèles GARCH fractionnellement intégrés surpassent les modèles GARCH de base en termes de prévision, en raison de la flexibilité accordée au degré de persistance des chocs de variance. Ces résultats sont utilisés pour modéliser conjointement les rendements et la volatilité des spreads de CDS dans l'ensemble des prochains essais. Le deuxième essai examine également les caractéristiques financières des marchés internationaux des CDS souverains, en donnant de nouvelles preuves sur leurs degrés d'efficacité. En utilisant un nouveau cadre économétrique basé sur une estimation du modèle VECM-FIGARCH en trois étapes, nous montrons que les informations contenues dans les spreads de CDS et les rendements des obligations sous-jacentes ne sont pas toujours reflétées instantanément et correctement dans le niveau du risque souverain. Les résultats révèlent l'existence d'opportunités d'arbitrage avec un rejet partiel de l'hypothèse de marche au hasard dans plusieurs des 37 pays étudiés [etc...] / Contagion phenomenon, efficiency hypothesis and spillover effects are amongst the most important economic theories as they provide an overall vision of the financial stability, yet the least understood in the aftermath of the recent crises. This thesis proposes to provide policy makers, investors and broadly market participants with an updated outlook of the dynamic behavior of the global sovereign Credit Default Swaps (CDS) markets: informational efficiency, interaction with other international financial markets and systemic-risk exposure. The steadily changing dynamics of these markets combined with the constantly evolving regulatory policies have led to a shared worldwide enthusiasm regarding the behavioral study of CDS markets, in which we contribute through five interconnected essays. We first discuss, in the first essay, the statistical characteristics of the sovereign CDS data, through the estimation of 9 GARCH-class models. This chapter compares the predictability performances of several linear and non-linear volatility models taking into consideration different financial stylized facts. Application on CDS spreads of 38 countries reveals that the forecasting power of these models depends on their ability to capture sovereign CDS features while estimating the variance process. Yet, the fractionally-integrated models outperform the basic GARCH-class models due to the allowed flexibility regarding the persistence degree of the variance shocks. These results are used to jointly model returns and volatility of CDS spreads in the forthcoming essays.The second essay also investigates the financial characteristics of the international sovereign CDS markets, by giving new evidences on their efficiency degrees. Using a new framework based on a 3-step estimation of a VECM-FIGARCH model, we show that information contained in CDS spreads and bond yields are not always instantaneously and properly reflected in the current sovereign risk level. Results reveal the existence of arbitrage opportunities with a partial rejection of the randomness hypothesis in some of the 37 studied countries. While the previous essay used the conditional expectation of CDS spreads to study the market behavior, the next essays rather focus on the properties of the variance and covariance. The predictability of sovereign CDS volatility, based on the information contained in some country-specific and global macroeconomic factors, is investigated in the third chapter [etc...]

In recent years the development and implementation of AI and machine learning models has increased dramatically. The availability of quality data paving the way for sophisticated AI models. Financial institutions uses many models in their daily operations. They are however, heavily regulated and need to follow the regulation that are set by central banks auditory standard and the financial supervisory authorities. One of these standards is the disclosure of expected credit losses in financial statements of banks, called IFRS 9. Banks must measure the expected credit shortfall in line with regulations set up by the EBA and FSA. In this master thesis, we are collaborating with a Swedish bank to evaluate different machine learning models to predict defaults of a unsecured credit portfolio. The default probability is a key variable in the expected credit loss equation. The goal is not only to develop a valid model to predict these defaults but to create and evaluate different models based on their performance and transparency. With regulatory challenges within AI the need to introduce transparency in models are part of the process. When banks use models there’s a requirement on transparency which refers to of how easily a model can be understood with its architecture, calculations, feature importance and logic’s behind the decision making process. We have compared the commonly used model logistic regression to three machine learning models, decision tree, random forest and XG boost. Where we want to show the performance and transparency differences of the machine learning models and the industry standard. We have introduced a transparency evaluation tool called transparency matrix to shed light on the different transparency requirements of machine learning models. The results show that all of the tree based machine learning models are a better choice of algorithm when estimating defaults compared to the traditional logistic regression. This is shown in the AUC score as well as the R2 metric. We also show that when models increase in complexity there is a performance-transparency trade off, the more complex our models gets the better it makes predictions. / Under de senaste ̊aren har utvecklingen och implementeringen av AI- och maskininl ̈arningsmodeller o ̈kat dramatiskt. Tillg ̊angen till kvalitetsdata banar va ̈gen fo ̈r sofistikerade AI-modeller. Finansiella institutioner anva ̈nder m ̊anga modeller i sin dagliga verksamhet. De a ̈r dock starkt reglerade och m ̊aste fo ̈lja de regler som faststa ̈lls av centralbankernas revisionsstandard och finansiella tillsynsmyndigheter. En av dessa standarder a ̈r offentligg ̈orandet av fo ̈rva ̈ntade kreditfo ̈rluster i bankernas finansiella rapporter, kallad IFRS 9. Banker m ̊aste ma ̈ta den fo ̈rva ̈ntade kreditfo ̈rlusten i linje med regler som faststa ̈lls av EBA och FSA. I denna uppsats samarbetar vi med en svensk bank fo ̈r att utva ̈rdera olika maskininl ̈arningsmodeller f ̈or att fo ̈rutsa ̈ga fallisemang i en blankokreditsportfo ̈lj. Sannolikheten fo ̈r fallismang ̈ar en viktig variabel i ekvationen fo ̈r fo ̈rva ̈ntade kreditfo ̈rluster. M ̊alet a ̈r inte bara att utveckla en bra modell fo ̈r att prediktera fallismang, utan ocks ̊a att skapa och utva ̈rdera olika modeller baserat p ̊a deras prestanda och transparens. Med de utmaningar som finns inom AI a ̈r behovet av att info ̈ra transparens i modeller en del av processen. Na ̈r banker anva ̈nder modeller finns det krav p ̊a transparens som ha ̈nvisar till hur enkelt en modell kan fo ̈rst ̊as med sin arkitektur, bera ̈kningar, variabel p ̊averkan och logik bakom beslutsprocessen. Vi har ja ̈mfo ̈rt den vanligt anva ̈nda modellen logistisk regression med tre maskininla ̈rningsmodeller: Decision trees, Random forest och XG Boost. Vi vill visa skillnaderna i prestanda och transparens mellan maskininl ̈arningsmodeller och branschstandarden. Vi har introducerat ett verktyg fo ̈r transparensutva ̈rdering som kallas transparensmatris fo ̈r att belysa de olika transparenskraven fo ̈r maskininla ̈rningsmodeller. Resultaten visar att alla tra ̈d-baserade maskininla ̈rningsmodeller a ̈r ett ba ̈ttre val av modell vid prediktion av fallisemang j ̈amfo ̈rt med den traditionella logistiska regressionen. Detta visas i AUC-score samt R2 va ̈rdet. Vi visar ocks ̊a att n ̈ar modeller blir mer komplexa uppst ̊ar en kompromiss mellan prestanda och transparens; ju mer komplexa v ̊ara modeller blir, desto ba ̈ttre blir deras prediktioner.

The combination of regulatory pressure and rare but impactful defaults together comprise the domain of low default portfolios, which is a central and complex topic that lacks clear industry standards. A novel approach that utilizes external data to create a Shadow Rating model has been proposed by Ulrich Erlenmaier. It addresses the lack of data by estimating a probability of default curve from an external rating scale and subsequently training a statistical model to estimate the credit rating of obligors. The thesis intends to first explore the capabilities of the Cohort model and the Pluto and Tasche model to estimate the probability of default associated with banks and financial institutions through the use of external data. Secondly, the thesis will implement a multinomial logistic regression model, an ordinal logistic regression model, Classification and Regression Trees, and a Random Forest model. Subsequently, their performance to correctly estimate the credit rating of companies in a portfolio of banks and financial institutions using financial data is evaluated. Results suggest that the Cohort model is superior in modelling the underlying data, given a Gini coefficient of 0.730 for the base case, as opposed to Pluto and Tasche's 0.260. Moreover, the Random Forest model displays marginally higher performance across all metrics (such as an accuracy of 57%, a mean absolute error of 0.67 and a multiclass receiver operating characteristic of 0.83). However, given a lower degree of interpretability, the more simplistic ordinal logistic regression model (50%, 0.80 and 0.81, respectively) can be preferred due to its clear interpretability and explainability. / Kombinationen av regulatoriskt påtryck och få men påverkande fallissemang utgör tillsammans området lågfallissemangsportföljer, vilket är ett centralt men komplext ämne med avsaknad av tydliga industristandarder. En metod som använder extern data för att skapa en skuggrating-modell har föreslagits av Ulrich Erlenmaier. Den adresserar problemet av bristande data genom att använda externa ratings för att estimera en kurva över sannolikheten. Sedermera implementeras en statistisk modell som estimerar kreditratingen av låntagare. Denna uppsats ämnar för det första att utforska möjligheterna för kohortmodellen samt Pluto-och-Tasche-modellen att estimera sannolikheten för fallissemang associerat med banker och finansiella institutioner genom användandet av extern data. För det andra implementeras statistiska modeller genom nominell logistisk regression, ordinal logistisk regression, klassificerings- och regressionsträd samt Random Forest. Sedermera utvärderas modellernas förmåga att förutse kreditratings för företag från en portfölj av banker och finansiella institutioner. Resultat föreslår att kohortmodellen är att föredra vid modellering av underliggande data, givet en Ginikoefficient på 0.730 för grundfallet, till skillnad från Pluto och Tasches resultat på 0.260. Vidare genererade Random Forest marginellt bättre resultat över alla utvärderingskriterier (till exempel, 57% träffsäkerhet, 0.67 mean absolute error och 0.83 multiclass receiver operating characteristic). Däremot har den en lägre tolkningsbarhet så att ordinal logistisk regression (med respektive värden 50%, 0.80 och 0.81) skulle kunna föredras, givet dess tydlighet och transparens.

This report seeks to thoroughly examine different approaches to estimating Loss Given Default through a comparison of traditional estimation methods, as well as a deeper variable analysis on micro, small, and medium-sized companies using primarily regression decision trees. The comparative study concluded that estimating loss given default depends heavily on business-specific factors and data variety. While regression models offer interpretability and machine learning techniques offer superior prediction, model selection should balance complexity, computational demands, implementation ease, and overall performance. From the variable analysis, loan size and guarantor property ownership emerged as key drivers for a lower Loss Given Default. / Denna rapport syftar till att grundligt undersöka olika metoder för att uppskatta Loss Given Default genom en jämförelse av traditionella skattningsmetoder samt en djupare variabelanalys av bolag med hjälp av främst regressionsbeslutsträd. I den jämförande studien drogs slutsatsen att uppskattningen av Loss Given Default beror i hög grad på företagsspecifika faktorer och olika typer av data. Medan regressionsmodeller erbjuder tolkningsmöjligheter och maskininlärningstekniker erbjuder överlägsna uppskattningar, bör valet av modell balansera komplexitet, beräkningskrav, enkelhet i genomförandet och övergripande prestanda. I variabelanalysen framkom lånestorlek och borgensmannens fastighetsinnehav som viktiga drivkrafter för en lägre Loss Given Default.

Die vorliegende Dissertation besteht aus drei Kapiteln über die Investmentfonds. Das erste Kapitel befasst sich mit der Rolle der Fondsmanager in der Bilanzverschönerung. Auf Basis der Analyse der Karrierewege von amerikanischen Fondsmanagern werden signifikante zusammenwirkende Manager-Fixed-Effects identifiziert, die nach der Kontrolle der endogenen Matching-Probleme immer noch robust sind. Die geschätzten Manager-Fixed-Effects haben signifikante Einflüsse auf die Out-of-Sample-Vorhersagen. Außerdem wird festgestellt, dass die Verriegelungen der Investmentfonds, die von gemeinsamen Managern verwaltet wurden, wichtige Kanäle für die Bilanzverschönerung verursachen. Das zweite Kapitel beschäftigt sich mit den Investmentstrategien der Fonds im Hinblick auf die Nutzung von Credit Default Swaps (CDS). Die Zuordnung der CDS-Positionen der Investmentfonds zu ihrem Bestandportfolio bietet eine neue Methodik zur Identifizierung der CDS-Strategien und kompensiert somit die Analysen der existierenden Literatur auf der Makroebene. Die Ergebnisse zeigen, dass die Anreize zur Risikoreduzierung die Spekulationsanreize dominieren, insbesondere, wenn die Kreditexposition durch ungedeckte Leerverkäufe der CDS-Verträge erhöht wird. Die erfahrenen Fondsmanager tendieren dazu, mehr Kreditrisiko in Kauf zu nehmen, während es für die Fondsmanagerinnen wahrscheinlicher als für ihre männlichen Kollegen ist, gegen das bestehende Risiko abzusichern. Der letzte Teil nimmt die Pleite von Lehman Brothers unter die Lupe, um sich mit der daraus resultierenden unerwarteten Schließung der CDS-Positionen als einem natürlichen Experiment auseinanderzusetzten. Diese Studie dient zur Untersuchung der Risiko- und Leistungsimplikationen der CDS-Investments der Fonds. Die Investmentfonds besitzen bei ihren CDS-Transaktionen im Durchschnitt einen beachtlichen Teil Extremrisiko. Während die CDS-Nutzer von guten Gesamtmarktlagen profitieren, erleiden sie unter Verlusten bei geclusterten Ausfällen. / This dissertation comprises of three chapters on mutual funds. The first chapter establishes the role of managers in the deceptive practice of window dressing. Employing comprehensive career history of U.S. mutual fund managers, I find strong jointly significant manager fixed effects, which are robust after addressing endogenous matching concerns. The estimated manager fixed effects are significant in making out-of-sample predictions. Further I establish that mutual fund interlocks through common managers are important channels that spread window dressing. The second chapter studies the investment strategies of mutual funds regarding their use of credit default swaps (CDS). Matches between mutual funds’ CDS positions and their underlying portfolio in the holdings facilitate a new approach in identifying CDS strategies that complements the “macro” level analyses in the existing literature. I find risk reducing incentives are dominated by speculative incentives, especially those to increase credit exposure via naked short CDS contracts. Experienced fund managers tend to take on more credit risk, while female managers are more likely to hedge comparing with their male peers. The third chapter employs the collapse of Lehman Brothers and the resulting sudden closures of CDS positions as a natural experiment to examine the risk and performance implications of mutual funds’ CDS investments. Funds on average load up on a significant amount of tail risk by trading CDS. While CDS users benefit when market conditions are favorable, they suffer during periods of clustered defaults.

Master of Agribusiness / Department of Agricultural Economics / Allen M. Featherstone / Institutions of the Farm Credit System (FCS) focus on risk-based lending in accordance with regulatory direction. The rating of risk also assists retail staff in loan approval, risk-based pricing, and allowance decisions. FCS institutions have developed models to analyze financial and related customer information in determining qualitative and quantitative risk measures. The objective of this thesis is to examine empirical account data from 2006-2012 to review the probability of default (PD) rating methodology within the overall risk rating system implemented by a Farm Credit System association. This analysis provides insight into the effectiveness of this methodology in predicting the migration of accounts across the association’s currently-established PD ratings where negative migration may be an apparent precursor to actual loan default. The analysis indicates that average PD ratings hold relatively consistent over the years, though the distribution of the majority of PD ratings shifted to higher quality by two rating categories over the time period. Various regressions run in the analysis indicate that the debt to asset ratio is most consistently statistically significant in estimating future PD ratings. The current ratio appears to be superior to working capital to gross profit as a liquidity measure in predicting PD rating migration. Funded debt to EBITDA is more effective in predicting PD rating movement as a measure of earnings to debt than gross profit to total liabilities, although the change of these ratios over time appear to be weaker indicators of the change in PD rating potentially due to the variable nature of annual earnings of production agriculture operations due to commodity price volatility. The debt coverage ratio is important as it relates to future PD migration, though the same variability in commodity price volatility suggests the need implement multi-year averaging for calculation of earnings-based ratios. These ratios were important in predicting the PD rating of observations one year into the future for production agriculture operations. To further test the predictive ability of the PD ratings, similar regression analyses were completed comparing current year rating and ratios to future PD ratings beyond one year, specifically for three and five years. Results from these regression models indicate that current year PD rating and ratios are less effective in predicting future PD ratings beyond one year. Furthermore, because of the variation in regression results between the analyses completed for one, three and five years into the future, it is important to regularly capture ratio and rating information, at least annually.